Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
619
result(s) for
"Kaiser, Jan"
Sort by:
Designing an adaptive production control system using reinforcement learning
Modern production systems face enormous challenges due to rising customer requirements resulting in complex production systems. The operational efficiency in the competitive industry is ensured by an adequate production control system that manages all operations in order to optimize key performance indicators. Currently, control systems are mostly based on static and model-based heuristics, requiring significant human domain knowledge and, hence, do not match the dynamic environment of manufacturing companies. Data-driven reinforcement learning (RL) showed compelling results in applications such as board and computer games as well as first production applications. This paper addresses the design of RL to create an adaptive production control system by the real-world example of order dispatching in a complex job shop. As RL algorithms are “black box” approaches, they inherently prohibit a comprehensive understanding. Furthermore, the experience with advanced RL algorithms is still limited to single successful applications, which limits the transferability of results. In this paper, we examine the performance of the state, action, and reward function RL design. When analyzing the results, we identify robust RL designs. This makes RL an advantageous control system for highly dynamic and complex production systems, mainly when domain knowledge is limited.
Journal Article
Hygromechanical Behavior of Polyamide 6.6: Experiments and Modeling
This paper investigates water absorption in polyamide 6.6 and the resulting hygroscopic swelling and changes in mechanical properties. First, sorption and swelling experiments on specimens from injection molded plates are presented. The observed swelling behavior is dependent on the melt flow direction of the injection molding process. Additionally, thermal analysis and mechanical tensile tests were performed for different conditioning states. The water sorption is accompanied by a decrease in the glass transition temperature and a significant reduction in stiffness and strength. Next, a sequentially coupled modeling approach is presented. A nonlinear diffusion model is followed by mechanical simulations accounting for swelling and concentration-dependent properties. For the mechanical properties, the notion of a “gap” temperature caused by the shift of the glass transition range due to water-induced plasticization is employed. This model enables the computation of local moisture concentration fields and the resultant swelling and changes in stress–strain behavior.
Journal Article
Assessing the Spectral Characteristics of Dye- and Pigment-Based Inkjet Prints by VNIR Hyperspectral Imaging
Fine art photography, paper documents, and other parts of printing that aim to keep value are searching for credible techniques and mediums suitable for long-term archiving purposes. In general, long-lasting pigment-based inks are used for archival print creation. However, they are very often replaced or forged by dye-based inks, with lower fade resistance and, therefore, lower archiving potential. Frequently, the difference between the dye- and pigment-based prints is hard to uncover. Finding a simple tool for countrified identification is, therefore, necessary. This paper assesses the spectral characteristics of dye- and pigment-based ink prints using visible near-infrared (VNIR) hyperspectral imaging. The main aim is to show the spectral differences between these ink prints using a hyperspectral camera and subsequent hyperspectral image processing. Two diverse printers were exploited for comparison, a hobby dye-based EPSON L1800 and a professional pigment-based EPSON SC-P9500. The identical prints created via these printers on three different types of photo paper were recaptured by the hyperspectral camera. The acquired pixel values were studied in terms of spectral characteristics and principal component analysis (PCA). In addition, the obtained spectral differences were quantified by the selected spectral metrics. The possible usage for print forgery detection via VNIR hyperspectral imaging is discussed in the results.
Journal Article
Reinforcement learning-trained optimisers and Bayesian optimisation for online particle accelerator tuning
Online tuning of particle accelerators is a complex optimisation problem that continues to require manual intervention by experienced human operators. Autonomous tuning is a rapidly expanding field of research, where learning-based methods like Bayesian optimisation (BO) hold great promise in improving plant performance and reducing tuning times. At the same time, reinforcement learning (RL) is a capable method of learning intelligent controllers, and recent work shows that RL can also be used to train domain-specialised optimisers in so-called reinforcement learning-trained optimisation (RLO). In parallel efforts, both algorithms have found successful adoption in particle accelerator tuning. Here we present a comparative case study, assessing the performance of both algorithms while providing a nuanced analysis of the merits and the practical challenges involved in deploying them to real-world facilities. Our results will help practitioners choose a suitable learning-based tuning algorithm for their tuning tasks, accelerating the adoption of autonomous tuning algorithms, ultimately improving the availability of particle accelerators and pushing their operational limits.
Journal Article
Genomic Instability and Radiation Risk in Molecular Pathways to Colon Cancer
Colon cancer is caused by multiple genomic alterations which lead to genomic instability (GI). GI appears in molecular pathways of microsatellite instability (MSI) and chromosomal instability (CIN) with clinically observed case shares of about 15-20% and 80-85%. Radiation enhances the colon cancer risk by inducing GI, but little is known about different outcomes for MSI and CIN. Computer-based modelling can facilitate the understanding of the phenomena named above. Comprehensive biological models, which combine the two main molecular pathways to colon cancer, are fitted to incidence data of Japanese a-bomb survivors. The preferred model is selected according to statistical criteria and biological plausibility. Imprints of cell-based processes in the succession from adenoma to carcinoma are identified by the model from age dependences and secular trends of the incidence data. Model parameters show remarkable compliance with mutation rates and growth rates for adenoma, which has been reported over the last fifteen years. Model results suggest that CIN begins during fission of intestinal crypts. Chromosomal aberrations are generated at a markedly elevated rate which favors the accelerated growth of premalignant adenoma. Possibly driven by a trend of Westernization in the Japanese diet, incidence rates for the CIN pathway increased notably in subsequent birth cohorts, whereas rates pertaining to MSI remained constant. An imbalance between number of CIN and MSI cases began to emerge in the 1980s, whereas in previous decades the number of cases was almost equal. The CIN pathway exhibits a strong radio-sensitivity, probably more intensive in men. Among young birth cohorts of both sexes the excess absolute radiation risk related to CIN is larger by an order of magnitude compared to the MSI-related risk. Observance of pathway-specific risks improves the determination of the probability of causation for radiation-induced colon cancer in individual patients, if their exposure histories are known.
Journal Article
Glacial Meltwater Identification in the Amundsen Sea
Pine Island Ice Shelf, in the Amundsen Sea, is losing mass because of warm ocean waters melting the ice from below. Tracing meltwater pathways from ice shelves is important for identifying the regions most affected by the increased input of this water type. Here, optimum multiparameter analysis is used to deduce glacial meltwater fractions from water mass characteristics (temperature, salinity, and dissolved oxygen concentrations), collected during a ship-based campaign in the eastern Amundsen Sea in February–March 2014. Using a one-dimensional ocean model, processes such as variability in the characteristics of the source water masses on shelf and biological productivity/respiration are shown to affect the calculated apparent meltwater fractions. These processes can result in a false meltwater signature, creating misleading apparent glacial meltwater pathways. An alternative glacial meltwater calculation is suggested, using a pseudo–Circumpolar Deep Water endpoint and using an artificial increase in uncertainty of the dissolved oxygen measurements. The pseudo–Circumpolar Deep Water characteristics are affected by the under ice shelf bathymetry. The glacial meltwater fractions reveal a pathway for 2014 meltwater leading to the west of Pine Island Ice Shelf, along the coastline.
Journal Article
Shape-specific characterization of colorectal adenoma growth and transition to cancer with stochastic cell-based models
Colorectal adenoma are precursor lesions on the pathway to cancer. Their removal in screening colonoscopies has markedly reduced rates of cancer incidence and death. Generic models of adenoma growth and transition to cancer can guide the implementation of screening strategies. But adenoma shape has rarely featured as a relevant risk factor. Against this backdrop we aim to demonstrate that shape influences growth dynamics and cancer risk. Stochastic cell-based models are applied to a data set of 197,347 Bavarian outpatients who had colonoscopies from 2006-2009, 50,649 patients were reported with adenoma and 296 patients had cancer. For multi-stage clonal expansion (MSCE) models with up to three initiating stages parameters were estimated by fits to data sets of all shapes combined, and of sessile (70% of all adenoma), peduncular (17%) and flat (13%) adenoma separately for both sexes. Pertinent features of adenoma growth present themselves in contrast to previous assumptions. Stem cells with initial molecular changes residing in early adenoma predominantly multiply within two-dimensional structures such as crypts. For these cells mutation and division rates decrease with age. The absolute number of initiated cells in an adenoma of size 1 cm is small around 10 3 , related to all bulk cells they constitute a share of about 10 −5 . The notion of very few proliferating stem cells with age-decreasing division rates is supported by cell marker experiments. The probability for adenoma transiting to cancer increases with squared linear size and shows a shape dependence. Compared to peduncular and flat adenoma, it is twice as high for sessile adenoma of the same size. We present a simple mathematical expression for the hazard ratio of interval cancers which provides a mechanistic understanding of this important quality indicator. We conclude that adenoma shape deserves closer consideration in screening strategies and as risk factor for transition to cancer.
Journal Article
Hardware Design for Autonomous Bayesian Networks
Directed acyclic graphs or Bayesian networks that are popular in many AI-related sectors for probabilistic inference and causal reasoning can be mapped to probabilistic circuits built out of probabilistic bits (p-bits), analogous to binary stochastic neurons of stochastic artificial neural networks. In order to satisfy standard statistical results, individual p-bits not only need to be updated sequentially but also in order from the parent to the child nodes, necessitating the use of sequencers in software implementations. In this article, we first use SPICE simulations to show that an autonomous hardware Bayesian network can operate correctly without any clocks or sequencers, but only if the individual p-bits are appropriately designed. We then present a simple behavioral model of the autonomous hardware illustrating the essential characteristics needed for correct sequencer-free operation. This model is also benchmarked against SPICE simulations and can be used to simulate large-scale networks. Our results could be useful in the design of hardware accelerators that use energy-efficient building blocks suited for low-level implementations of Bayesian networks. The autonomous massively parallel operation of our proposed stochastic hardware has biological relevance since neural dynamics in brain is also stochastic and autonomous by nature.
Journal Article
Ischemic Heart Disease in Workers at Mayak PA: Latency of Incidence Risk after Radiation Exposure
We present an updated analysis of incidence and mortality from atherosclerotic induced ischemic heart diseases in the cohort of workers at the Mayak Production Association (PA). This cohort constitutes one of the most important sources for the assessment of radiation risk. It is exceptional because it comprises information on several other risk factors. While most of the workers have been exposed to external gamma radiation, a large proportion has additionally been exposed to internal radiation from inhaled plutonium. Compared to a previous study by Azizova et al. 2012, the updated dosimetry system MWDS-2008 has been applied and methods of analysis have been revised. We extend the analysis of the significant incidence risk and observe that main detrimental effects of external radiation exposure occur after more than about 30 years. For mortality, significant risk was found in males with an excess relative risk per dose of 0.09 (95% CI: 0.02; 0.16) [Formula: see text] while risk was insignificant for females. With respect to internal radiation exposure no association to risk could be established.
Journal Article